Updated

Qdrant vs Weaviate

Of the 107 makers' products we know the vector database of, 18 chose Qdrant (17%) and 16 Weaviate (15%); 1 uses both. Among the 42 launched in 2025, Qdrant is in 19% and Weaviate in 2%. At our calculator's default usage, Qdrant comes to $103 a month and Weaviate $253, at list prices.

Two open-source vector store options for vector database. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

Which fits you

Choose Qdrant if
  • You need an open-source store with heavy filtering or hybrid search, self-hosted or managed

Use it whenYour queries combine similarity with many filters, such as tenant, date and category.

Trade-offOne more service to deploy and keep in sync with your main database.

Choose Weaviate if
  • You need an open-source store with heavy filtering or hybrid search, self-hosted or managed

Use it whenUsers search with both exact terms and meaning, and you want both in one query.

Trade-offMore concepts and configuration to learn than simpler stores; some advanced features need a license key.

At a glance

QdrantWeaviate
Used by18 makers' products · 94 open-source projects16 makers' products · 32 open-source projects
Cost at default usagevectors stored 1 million vectors, queries 1 million queries, vectors written or updated 500k writes$103/mo Standard (3 nodes, 0.5 vCPU / 4 GiB each)$253/mo Flex
Downloads810.5k/wk−13% vs npm344.8k/wk−72% vs npm
PricingFree and open source to self-host; Qdrant Cloud has a free tier plus usage-based paid plans. · paid from Usage-based, no minimumCore engine free to self-host (BSD-3-Clause); Weaviate Cloud has an always-free tier and pay-as-you-go plans from $45/month; some advanced features require a license key. · paid from $45/mo
Free tierYesYes
Open sourceYes · self-hostableYes · self-hostable

Which makers on your framework pick

Makers' products built with each framework that chose either one, for vector database.

FrameworkQdrantWeaviate
Next.js52All 38 Next.js products' picks →

New launches vs older products

A tool that came first has products from every year since, so its total runs ahead. Here is what products launched each year chose, as a share of those that made the vector database decision (by the year they launched on Product Hunt).

LaunchedQdrantWeaviateProducts
202425% 718% 528
202519% 82% 142

Cost as you grow

Both cost $0 up to 100k vectors; from 500k vectors Qdrant costs less ($68 vs $126); and still does at 100M vectors ($8,747 vs $25,259).

$0$1,000$5,000$10,000$20,0000.10.5151050100
WeaviateQdrantx: vectors stored (1,536 dimensions, about 6 gb per million) (million vectors), other usage scaled with it · cheapest usable plan at each point, list prices · try your own numbers
The numbers, plan by plan
Vectors stored (1,536 dimensions, about 6 GB per million)QdrantWeaviate
0.1$0 Free$0 Free
0.5$68 Standard (1 node, 1 vCPU / 8 GiB)$126 Flex
1$103 Standard (3 nodes, 0.5 vCPU / 4 GiB each)$253 Flex
5$410 Standard (3 nodes, 2 vCPU / 16 GiB each)$1,263 Flex
10$820 Standard (3 nodes, 4 vCPU / 32 GiB each)$2,526 Flex
50$4,374 Standard (2 nodes, 32 vCPU / 256 GiB each)$12,629 Flex
100$8,747 Standard (4 nodes, 32 vCPU / 256 GiB each)$25,259 Flex

From each vendor's pricing page: Qdrant, Weaviate.

What makers say

Makers on using it for vector database, from Product Hunt and Starter Story interviews, each linked to the source. Products with a page of their own and fuller notes first.

On Qdrant
After evaluating a bunch of Vector DBs to be our internal vector DB, we finally closed on QDrant because it was the one that scaled the best and had the best price performance ratio
Conva.AI, the makerSep 2026 ↗
Thanks to Qdrant, we utilize it as a vector database to store our knowledge base and uploaded file data. Our RAG would not be possible without it.
AICamp, the makerSep 2026 ↗
We evaluated a bunch of vector DBs—and Qdrant stood out for its blazing speed, filtering, and hybrid search. It's the unsung hero that lets our AI agents recall and reason across docs, CRMs, and conversations in milliseconds.
Zams, the makerSep 2026 ↗
12 more on the Qdrant page →
On Weaviate
To store all our vector embeddings, now a staple for us to build forward. Their automatic 'load balancing' on which vectors are recently used is a game changer for system optimization
Quantera.ai, the makerSep 2026 ↗
Weaviate gives us fast, semantic search across unstructured call data, crucial for surfacing insights in real time. Its native vector support and scalability made it the best fit for building an AI native platform like Insight7.
Insight7, the makerSep 2026 ↗
We use Weaviate as a our vector database. Our main feed feature is powered by the vector embeddings Weaviate generates.
Depth, the makerSep 2026 ↗
5 more on the Weaviate page →

Loved and watch-outs

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

Qdrant
Most loved
  • It is fast and scales with strong price-performance, helped by its Rust core. PH
  • Payload filtering and hybrid semantic plus boolean search work together. PH
  • Runs easily self-hosted in Docker, a common pick for local RAG and agent memory. PHHNHN 2HN 3
Watch-outs
  • As a separate server it is slower than in-process stores for small local datasets. HN
  • Setting up and operating a vector database is overkill for teams that just need working search. HNHN 2
On Product Hunt: 5.0★, 23 reviews · mentioned most: fast performance, semantic search, excellent documentation
Weaviate
Most loved
  • Open source and free to run, with good docs and an active, friendly community. HNweaviate.ioPHHN 2
  • Scales to production workloads, including multi-tenant setups on its managed cloud. weaviate.ioPHPH 2weaviate.io 2
  • Built-in vectorization and a GraphQL API let queries mix semantic search with structured data. PHHNHN 2
Watch-outs
  • Search can be slow, with metadata filtering hurting vector query performance and hosted retrieval latency complaints. HNHN 2
On Product Hunt: 4.9★, 13 reviews · mentioned most: vector embeddings

Who uses each

Used by both — often one replacing the other, or each for a different part of the product

What makers pair each with

pgvectorInside your databaseApps already on Postgres that want vector search in the same database, joined with normal tables.
ChromaEmbedded / local-firstPrototyping RAG on your laptop with a pip or npm install and no server to run.vs Qdrant →
PineconeManaged vector storeA fully hosted index with nothing to operate, sized by usage.vs Qdrant →vs Weaviate →
turbopufferManaged vector storeVery large or many-tenant indexes where storing everything on object storage keeps cost down.vs Qdrant →

Questions

Qdrant or Weaviate: which do makers choose?

Of the 107 makers' products we know the vector database of, 18 chose Qdrant (17%) and 16 Weaviate (15%); 1 uses both. Among the 42 launched in 2025, Qdrant is in 19% and Weaviate in 2%. At our calculator's default usage, Qdrant comes to $103 a month and Weaviate $253, at list prices. Choose Qdrant if you need an open-source store with heavy filtering or hybrid search, self-hosted or managed; choose Weaviate if you need an open-source store with heavy filtering or hybrid search, self-hosted or managed.

When should I pick Qdrant over Weaviate?

Pick Qdrant if: You need an open-source store with heavy filtering or hybrid search, self-hosted or managed.

When should I pick Weaviate over Qdrant?

Pick Weaviate if: You need an open-source store with heavy filtering or hybrid search, self-hosted or managed.

Which is cheaper, Qdrant or Weaviate?

At vectors stored 1 million vectors, queries 1 million queries, vectors written or updated 500k writes: Qdrant $103/mo (Standard (3 nodes, 0.5 vCPU / 4 GiB each)), Weaviate $253/mo (Flex), at list prices.

How do Qdrant and Weaviate compare in cost as you grow?

Both cost $0 up to 100k vectors; from 500k vectors Qdrant costs less ($68 vs $126); and still does at 100M vectors ($8,747 vs $25,259). Cheapest usable plan at each scale, at list prices.